June 2026
- 🧮 i8 vector type for quantization-aware models (75% reduced storage and query cost compared to
f32)
Fetched June 10, 2026
More from turbopuffer
- May 2026May 1, 2026
- 🌿 Namespace branching: instant copy-on-write namespace cloning - ✏️ Typo-tolerant string matching with the Fuzzy filter - 🗺️ View names…
turbopuffer · Changelog - April 2026Apr 1, 2026
- 📌 Pin a namespace to cache for lower cost at high QPS - 🕸️ Support for sparse vector search - ↔️ GCP <- AWS namespace copies with [copy…
turbopuffer · Changelog
